{"id":"https://openalex.org/W2039678943","doi":"https://doi.org/10.1145/1571941.1572013","title":"Quantifying performance and quality gains in distributed web search engines","display_name":"Quantifying performance and quality gains in distributed web search engines","publication_year":2009,"publication_date":"2009-07-19","ids":{"openalex":"https://openalex.org/W2039678943","doi":"https://doi.org/10.1145/1571941.1572013","mag":"2039678943"},"language":"en","primary_location":{"id":"doi:10.1145/1571941.1572013","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1572013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015615642","display_name":"B. Barla Cambazo\u011flu","orcid":"https://orcid.org/0000-0003-2192-3819"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"B Barla Cambazoglu","raw_affiliation_strings":["Yahoo! Research, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Barcelona, Spain","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110866799","display_name":"Vassilis Plachouras","orcid":null},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Vassilis Plachouras","raw_affiliation_strings":["Yahoo! Research, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Barcelona, Spain","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076204770","display_name":"Ricardo Baeza\u2010Yates","orcid":"https://orcid.org/0000-0003-3208-9778"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ricardo Baeza-Yates","raw_affiliation_strings":["Yahoo! Research, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Barcelona, Spain","institution_ids":["https://openalex.org/I2800095910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015615642"],"corresponding_institution_ids":["https://openalex.org/I2800095910"],"apc_list":null,"apc_paid":null,"fwci":13.9453,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.98600926,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"411","last_page":"418"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9753999710083008,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8788213729858398},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.7084879875183105},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.6820676922798157},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6252003908157349},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5446585416793823},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.5321502089500427},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5243690013885498},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.5219244956970215},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.5033647418022156},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.4545733630657196},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.44930532574653625},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4454878270626068},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.4380408823490143},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4261438846588135},{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.4195922315120697},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.382824182510376},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2690500020980835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8788213729858398},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.7084879875183105},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.6820676922798157},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6252003908157349},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5446585416793823},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.5321502089500427},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5243690013885498},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.5219244956970215},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.5033647418022156},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.4545733630657196},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.44930532574653625},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4454878270626068},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4380408823490143},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4261438846588135},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.4195922315120697},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.382824182510376},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2690500020980835},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1571941.1572013","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1572013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.936.6410","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.936.6410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Berkant_Cambazoglu/publication/221300213_Quantifying_performance_and_quality_gains_in_distributed_web_search_engines/links/0912f50b7cbef3c72e000000.pdf?origin%3Dpublication_detail","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.947.2044","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.947.2044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Berkant_Cambazoglu/publication/221300213_Quantifying_Performance_and_Quality_Gains_in_Distributed_Web_Search_Engines/links/0912f50b7cbef3c72e000000.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W140310380","https://openalex.org/W191231183","https://openalex.org/W232533489","https://openalex.org/W1488690452","https://openalex.org/W1566845903","https://openalex.org/W2007687650","https://openalex.org/W2029341294","https://openalex.org/W2030649419","https://openalex.org/W2082973176","https://openalex.org/W2086253379","https://openalex.org/W2099111758","https://openalex.org/W2113184419","https://openalex.org/W2121928206","https://openalex.org/W2122166301","https://openalex.org/W2123127954","https://openalex.org/W2160484851","https://openalex.org/W2295141584","https://openalex.org/W2621280964","https://openalex.org/W4255459561","https://openalex.org/W6671120260"],"related_works":["https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2964752624","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W2095543197","https://openalex.org/W2371838993"],"abstract_inverted_index":{"Distributed":[0],"search":[1,67,114,152],"engines":[2],"based":[3,70],"on":[4,71,81],"geographical":[5],"partitioning":[6],"of":[7,21,34,63,90,119,158],"a":[8,14,64],"central":[9],"Web":[10,94,137,142],"index":[11,73],"emerge":[12],"as":[13,116],"feasible":[15],"solution":[16],"to":[17,58,86,112,140,146],"the":[18,22,38,60,87,117,151,156],"immense":[19],"growth":[20],"Web,":[23],"user":[24],"bases,":[25],"and":[26,40,75,93,144],"query":[27,76,91,107],"traffic.":[28],"However,":[29],"there":[30],"is":[31],"still":[32],"lack":[33],"research":[35],"in":[36],"quantifying":[37],"performance":[39,61,83],"quality":[41],"gains":[42,84],"that":[43,99,135],"can":[44,109,125],"be":[45,110,127],"achieved":[46,104],"by":[47,105],"such":[48],"architectures.":[49],"In":[50],"this":[51,149],"paper,":[52],"we":[53,79],"develop":[54],"various":[55],"cost":[56],"models":[57],"evaluate":[59],"benefits":[62],"geographically":[65],"distributed":[66,88,106,136],"engine":[68],"architecture":[69],"partial":[72],"replication":[74],"forwarding.":[77],"Specifically,":[78],"focus":[80],"possible":[82],"due":[85],"nature":[89],"processing":[92,108],"crawling":[95,138],"processes.":[96],"We":[97,132,154],"show":[98,134],"any":[100],"response":[101],"time":[102],"gain":[103],"utilized":[111],"improve":[113],"relevance":[115],"use":[118],"complex":[120],"but":[121],"more":[122],"accurate":[123],"algorithms":[124],"now":[126],"enabled":[128],"for":[129],"document":[130],"ranking.":[131],"also":[133],"leads":[139],"better":[141],"coverage":[143],"try":[145],"see":[147],"if":[148],"improves":[150],"quality.":[153],"verify":[155],"validity":[157],"our":[159],"claims":[160],"over":[161],"large,":[162],"real-life":[163],"datasets":[164],"via":[165],"simulations.":[166]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
